中文
相关论文

相关论文: Related Knowledge Perturbation Matters: Rethinking…

200 篇论文

Knowledge editing aims to update the embedded knowledge within Large Language Models (LLMs). However, existing approaches, whether through parameter modification or external memory integration, often suffer from inconsistent evaluation…

计算与语言 · 计算机科学 2025-05-27 Guoxiu He , Xin Song , Futing Wang , Aixin Sun

Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations. Traditional updating methods, like fine-tuning and incremental…

计算与语言 · 计算机科学 2025-04-30 Yifan Wei , Xiaoyan Yu , Ran Song , Hao Peng , Angsheng Li

Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various solutions for knowledge updating, they often struggle with…

人工智能 · 计算机科学 2025-06-17 Zichuan Fu , Xian Wu , Guojing Li , Yingying Zhang , Yefeng Zheng , Tianshi Ming , Yejing Wang , Wanyu Wang , Xiangyu Zhao

Knowledge Editing (KE) for modifying factual knowledge in Large Language Models (LLMs) has been receiving increasing attention. However, existing knowledge editing methods are entity-centric, and it is unclear whether this approach is…

计算与语言 · 计算机科学 2023-11-16 Yifan Wei , Xiaoyan Yu , Huanhuan Ma , Fangyu Lei , Yixuan Weng , Ran Song , Kang Liu

As large language models continue to scale up, knowledge editing techniques that modify models' internal knowledge without full retraining have gained significant attention. MEMIT, a prominent batch editing algorithm, stands out for its…

计算与语言 · 计算机科学 2025-09-10 Zilu Dong , Xiangqing Shen , Rui Xia

Despite their exceptional capabilities, large language models (LLMs) are prone to generating unintended text due to false or outdated knowledge. Given the resource-intensive nature of retraining LLMs, there has been a notable increase in…

计算与语言 · 计算机科学 2024-05-28 Jun-Yu Ma , Zhen-Hua Ling , Ningyu Zhang , Jia-Chen Gu

Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training,…

Knowledge represented in Large Language Models (LLMs) is quite often incorrect and can also become obsolete over time. Updating knowledge via fine-tuning is computationally resource-hungry and not reliable, and so knowledge editing (KE) has…

计算与语言 · 计算机科学 2023-12-21 Weixuan Wang , Barry Haddow , Alexandra Birch

Knowledge editing is a rising technique for efficiently updating factual knowledge in large language models (LLMs) with minimal alteration of parameters. However, recent studies have identified side effects, such as knowledge distortion and…

Recently, knowledge editing (KE) has emerged as a promising approach to update specific facts in Large Language Models (LLMs) without the need for full retraining. Despite the effectiveness in general-domain benchmarks, their applicability…

计算与语言 · 计算机科学 2026-02-17 Shigeng Chen , Linhao Luo , Zhangchi Qiu , Yanan Cao , Carl Yang , Shirui Pan

Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge.…

计算与语言 · 计算机科学 2025-06-04 Keyuan Cheng , Zijian Kan , Zhixian He , Zhuoran Zhang , Muhammad Asif Ali , Ke Xu , Lijie Hu , Di Wang

Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, which can manifest as misreading and misrecognition errors due to the complexity of multimodal knowledge. Previous benchmarks have not…

计算机视觉与模式识别 · 计算机科学 2024-10-31 Junzhe Zhang , Huixuan Zhang , Xunjian Yin , Baizhou Huang , Xu Zhang , Xinyu Hu , Xiaojun Wan

Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing…

Knowledge editing methods for large language models are commonly evaluated using predefined benchmarks that assess edited facts together with a limited set of related or neighboring knowledge. While effective, such evaluations remain…

计算与语言 · 计算机科学 2026-05-12 Shuainan Liu , Xuanang Chen , Ben He , Le Sun

Model editing has been gaining increasing attention over the past few years. For Knowledge Editing in particular, more challenging evaluation datasets have recently been released. These datasets use different methodologies to score the…

计算与语言 · 计算机科学 2025-07-09 Sebastian Pohl , Max Ploner , Alan Akbik

Knowledge Editing (KE) aims to adjust a Large Language Model's (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurring the computational expense of re-training the entire model.…

计算与语言 · 计算机科学 2025-05-29 Liyu Zhang , Weiqi Wang , Tianqing Fang , Yangqiu Song

Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited…

计算与语言 · 计算机科学 2025-05-20 Jiakuan Xie , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

The extensive utilization of large language models (LLMs) underscores the crucial necessity for precise and contemporary knowledge embedded within their intrinsic parameters. Existing research on knowledge editing primarily concentrates on…

计算与语言 · 计算机科学 2025-02-20 Zihao Wei , Jingcheng Deng , Liang Pang , Hanxing Ding , Huawei Shen , Xueqi Cheng

The swift advancement in Multimodal LLMs (MLLMs) also presents significant challenges for effective knowledge editing. Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Kaihang Pan , Zhaoyu Fan , Juncheng Li , Qifan Yu , Hao Fei , Siliang Tang , Richang Hong , Hanwang Zhang , Qianru Sun

Knowledge Editing is a technique that updates large language models (LLMs) with new information to maintain their world knowledge. This approach avoids the need to rebuild the model from scratch, thereby addressing the high costs associated…

计算与语言 · 计算机科学 2025-09-09 Changyue Wang , Weihang Su , Qingyao Ai , Yichen Tang , Yiqun Liu
‹ 上一页 1 2 3 10 下一页 ›